MiniMax M3.1 Flash is now on NanoGPT, included in your subscription.
Built for coding and tool use, with text, image and video input, a 1M-token context, and always-on reasoning.
https://nano-gpt.com/conversation?model=minimax%2Fminimax-m3.1-flash
Filtering by: minimax · clear filter
Relight an existing video with MiniMax H3 Max Relight on NanoGPT.
Upload your clip and a lighting-sphere reference to change the look of the shot. Output options run from 480p to 2K.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Frelight
MiniMax H3 Max Recast is now on NanoGPT.
Replace people in a video using 1-4 reference photos while preserving the original motion, camera, cuts and soundtrack. Supports 5-30 second source clips.
Individual shots must be no longer than 15 seconds.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Frecast
Your video doesn't have to end there.
MiniMax H3 Max Extend is now on NanoGPT. Upload a clip, describe what happens next, and request 5-15 seconds of new footage at up to 2K.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Fextend-video
MiniMax H3 Max Lip Sync is now on NanoGPT.
Add a portrait and a voice or music track to make it talk or sing, with synchronized mouth movement and output from 480p through 2K.
Audio must be at least 5 seconds. Longer tracks are clipped to the first 15 seconds.
Try it:
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Flip-sync%2Fimage-to-video
Give the video model a character, a scene and a sound to work from.
MiniMax H3 Reference-to-Video + Singularity are now on NanoGPT: guide clips with image/video/audio references, or animate a starting image.
3-15 seconds, with native stereo audio.
Reference-to-Video:
https://nano-gpt.com/media?mode=video&model=minimax-h3%2Freference-to-video
Singularity:
https://nano-gpt.com/media?mode=video&model=minimax-h3-singularity%2Fimage-to-video
P-Video 2 Pro is now on NanoGPT, built on MiniMax H3.
Turn text or a still image into 5-15 second clips with generated audio.
Choose Speed or Quality mode, with optional last-frame guidance for image-to-video.
Text-to-video:
https://nano-gpt.com/media?mode=video&model=pruna-ai%2Fp-video-2-pro%2Ftext-to-video
Image-to-video:
https://nano-gpt.com/media?mode=video&model=pruna-ai%2Fp-video-2-pro%2Fimage-to-video
MiniMax H3 Max Multi Angle is now on NanoGPT.
Turn a still image into a moving camera shot: orbit around a subject, push in for detail, pull back or rise above the scene. Use camera presets or custom keyframes.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max%2Fmulti-angle%2Fimage-to-video
MiniMax H3 Max now supports reference-based video generation on NanoGPT.
Guide a new shot with image, video and audio references, alongside the existing text and first/last-frame modes.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max
MiniMax H3 Max and H3 Max Turbo now support native 1080p on NanoGPT.
Create 5-15 second Full HD videos from text or animate an image, with optional first/last-frame transitions.
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max
MiniMax H3 Image and Image Edit are now on NanoGPT.
Create portraits and cinematic scenes, or change outfits, backgrounds and styles using reference images.
Up to 2K output. Editing supports up to 9 reference images.
https://nano-gpt.com/media?mode=image&model=wavespeed-ai%2Fminimax-h3%2Ftext-to-image
MiniMax H3 Spicy Image-to-Video is now available on NanoGPT.
Animate a reference image with expressive, unrestricted motion and native stereo audio, or guide the transition toward an optional final frame for more controlled cinematic clips.
Try it:
https://nano-gpt.com/media?mode=video&model=wavespeed-ai%2Fminimax-h3%2Fimage-to-video-spicy
MiniMax H3 just got two major upgrades on NanoGPT.
MiniMax H3 Max Turbo runs at roughly twice the speed and half the cost while targeting 97% of H3 Max quality. Generate from text, animate a starting image, or guide a transition with first and last frames.
MiniMax H3 can also edit or extend existing videos, with optional image and audio references and original-audio preservation.
Try H3 Max Turbo:
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max-turbo
Edit or extend with H3:
MiniMax H3 Max is now available on NanoGPT.
Create videos from a text prompt, animate a starting image, or guide a controlled transition with optional first and last frames. One unified model automatically switches between text-to-video and image-to-video based on your inputs.
Try it:
https://nano-gpt.com/media?mode=video&model=minimax%2Fh3-max
MiniMax Music 3 is now available on NanoGPT.
Create complete songs up to five minutes long from a detailed prompt. Add structured lyrics, let the model write them, or switch to instrumental-only mode.
Try it:
https://nano-gpt.com/media?mode=audio&model=minimax%2Fmusic-3